Paper Title
Recruitment Success Predictor using Machine Learning using Random Forest Method

Abstract
The project is aimed at helping Human Resources group to increase their efficiency of hiring process. Due to the pandemic, there has been a shift in the Indian IT landscape and service industry. There has been a significant demand for high skill labor in the market due to influx of demands. This has given the employees more career options and competitive compensation structures. This dynamic has resulted in increased percentage of resources not joining the firms whose offer has been accepted earlier. Being at the end of the value chain of recruitment process, “Employee Onboarding” efficiency was impacted from the 30-50% on an average, resulting in loss of efforts and impacting project start dates thereby having a significant blow to the bottom line. There was a need to predict if resource would join the firm during the early stages of recruitment so back up strategies can be instituted. The solution we proposed involves making use of historical candidate data to build a model that will allow predict likelihood of an offer drop. This solution makes use of features such as skills, candidate characteristics such as experience, gender, hiring level, compensation offered and other relevant offer details. However, the model would not be able to make use of candidates’ personal choices that may have resulted in offer drop. Keywords - Artificial Intelligence, Machine Learning, Decision Tree, Random Forest Method, Recruitment, Human Resources, Probability, Employee Onboarding, Regression, Supervised Learning, Database, Brier Scoring